scientific-visualization

Create publication figures with matplotlib/seaborn/plotly. Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF, for journal-ready scientific plots.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/scientific-visualization/SKILL.md

Quality

Content

56%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill is highly actionable with a clear workflow and well-organized bundle references, but it is notably verbose and violates progressive disclosure by inlining a large seaborn tutorial that duplicates reference material. Trimming the seaborn section and pointing to a reference file would substantially improve both conciseness and structure.

Suggestions

Move the bulk of the seaborn tutorial (lines ~354-644) into a references/seaborn_guide.md file and keep only a short worked example plus a pointer in SKILL.md.

Cut concept re-explanations Claude already knows (e.g. 'Seaborn provides a high-level, dataset-oriented interface...') and the duplicated styling guidance to reduce token load.

Resolve the nested scientific-packages/seaborn/SKILL.md pointer — either bundle the needed seaborn content locally or replace it with a single-level local reference so navigation stays one level deep.

Dimension	Reasoning	Score
Conciseness	The ~250-line seaborn section (roughly lines 354-644) re-explains seaborn concepts and advantages Claude already knows and duplicates matplotlib styling guidance, with many redundant code blocks, making it noticeably verbose rather than just minor padding.	2 / 5
Actionability	Most guidance is executable, copy-paste-ready code with concrete function calls (save_publication_figure, configure_for_journal, check_figure_size); only minor gaps like a few '# ...' placeholders and an undefined 'df' keep it from a 5.	4 / 5
Workflow Clarity	The Workflow Summary gives a clear Plan→Configure→Create→Verify→Export→Review sequence with an explicit verify checkpoint (check_figure_size) and a Final Checklist, but the verify/review steps are lighter than a full validate-fix-retry loop.	4 / 5
Progressive Disclosure	A good Resources section lists one-level-deep references to real bundle files, but the inlined ~250-line seaborn section clearly belongs in a separate reference, and the pointer to scientific-packages/seaborn/SKILL.md introduces a 2+-level reference chain.	3 / 5
	Total	13 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and capability-rich with strong trigger terms and a clear niche, but it omits an explicit 'Use when...' trigger clause, which caps its completeness. Adding a concrete usage trigger would raise the completeness score.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when preparing figures for journal submission, multi-panel plots, or colorblind-safe publication graphics.'

Include a couple of plain user phrasings (e.g. 'make a publication plot', 'figure for my manuscript') alongside the technical terms to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Multi-panel layouts, error bars, significance markers, colorblind-safe, export PDF/EPS/TIFF" — giving comprehensive capability coverage, matching the score-5 anchor.	5 / 5
Completeness	It clearly states the "what" but has no explicit "Use when..." trigger clause — timing is only weakly implied by "for journal-ready scientific plots," which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good natural-term coverage ("publication figures", "matplotlib/seaborn/plotly", "journal-ready scientific plots", PDF/EPS/TIFF extensions), but a few common user phrasings ("make a plot", "figure for my paper") are absent, so it sits above the midpoint but not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The publication/journal-ready scientific-plot niche is mostly distinct from generic plotting skills with only minor overlap risk, fitting the score-4 anchor better than the broader score-3 or fully-distinct score-5.	4 / 5
	Total	16 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (774 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/scientific-visualization/SKILL.md
Commit: ddcaa2a

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.